> ## Documentation Index > Fetch the complete documentation index at: https://docs.haiqu.ai/llms.txt > Use this file to discover all available pages before exploring further. # Load Classical Data With Data Loading > Submit a classical-to-quantum data-loading job and return polling context. Use this tool when the caller needs a generated circuit from classical data before execution or later circuit analysis. The request must use one of the supported ``dl_type`` values, and the response schema is a lightweight ``{"context": ...}`` wrapper rather than a structured job object. When to Use: - Call this when classical data must be turned into a circuit before execution or later circuit analysis. - Call this when the user has already chosen a concrete data-loading mode such as ``DistributionLoading`` or ``VectorLoading``. Constraints: - ``dl_type`` must be exactly one of ``DistributionLoading``, ``VectorLoading``, ``BlockVectorLoading``, ``MpsLoading``, ``EntangledManifoldEmbedding``, or ``FunctionLoading``. - MCP-layer validation checks required parameter keys for the selected mode and enforces the ``BlockVectorLoading`` exclusivity rule. - The MCP layer does not reject every unknown extra key or fully validate parameter value domains before delegating to the backend. Notes: - ``DistributionLoading`` prepares a probability distribution state. - ``VectorLoading`` prepares an arbitrary real or complex vector state. - ``MpsLoading`` prepares an arbitrary state from a matrix product state. - ``BlockVectorLoading`` prepares a block-wise vector or matrix state. - ``EntangledManifoldEmbedding`` encodes real data into a quantum state with controllable entanglement. - ``FunctionLoading`` prepares the values of a single-variable function ``f(x)`` as amplitudes; ``func`` is a math expression string in ``x``. - After submission, callers should use ``get_job_results_and_status`` to retrieve terminal outputs such as the generated circuit ID. Args: user: Authenticated user resolved from the API key. data: Data-loading payload. ``dl_type`` must be exactly one of ``DistributionLoading``, ``VectorLoading``, ``BlockVectorLoading``, ``MpsLoading``, ``EntangledManifoldEmbedding``, or ``FunctionLoading``. db: Active database session. Returns: A lightweight context wrapper summarizing the submission and next polling step. Raises: HTTPException: Raised with ``404`` if the experiment is unavailable for the user, or ``400`` if payload validation fails. ## OpenAPI ````yaml https://api.haiqu.ai/openapi.json post /ai/load_classical_data_with_data_loading openapi: 3.1.0 info: title: Haiqu API summary: Haiqu RESTful API service. description: Cloud service providing the access to Haiqu cloud runtime contact: name: Haiqu Inc. url: https://haiqu.ai/ email: info@haiqu.ai version: 1.4.0 servers: [] security: [] paths: /ai/load_classical_data_with_data_loading: post: summary: Load Classical Data With Data Loading description: >- Submit a classical-to-quantum data-loading job and return polling context. Use this tool when the caller needs a generated circuit from classical data before execution or later circuit analysis. The request must use one of the supported ``dl_type`` values, and the response schema is a lightweight ``{"context": ...}`` wrapper rather than a structured job object. When to Use: - Call this when classical data must be turned into a circuit before execution or later circuit analysis. - Call this when the user has already chosen a concrete data-loading mode such as ``DistributionLoading`` or ``VectorLoading``. Constraints: - ``dl_type`` must be exactly one of ``DistributionLoading``, ``VectorLoading``, ``BlockVectorLoading``, ``MpsLoading``, ``EntangledManifoldEmbedding``, or ``FunctionLoading``. - MCP-layer validation checks required parameter keys for the selected mode and enforces the ``BlockVectorLoading`` exclusivity rule. - The MCP layer does not reject every unknown extra key or fully validate parameter value domains before delegating to the backend. Notes: - ``DistributionLoading`` prepares a probability distribution state. - ``VectorLoading`` prepares an arbitrary real or complex vector state. - ``MpsLoading`` prepares an arbitrary state from a matrix product state. - ``BlockVectorLoading`` prepares a block-wise vector or matrix state. - ``EntangledManifoldEmbedding`` encodes real data into a quantum state with controllable entanglement. - ``FunctionLoading`` prepares the values of a single-variable function ``f(x)`` as amplitudes; ``func`` is a math expression string in ``x``. - After submission, callers should use ``get_job_results_and_status`` to retrieve terminal outputs such as the generated circuit ID. Args: user: Authenticated user resolved from the API key. data: Data-loading payload. ``dl_type`` must be exactly one of ``DistributionLoading``, ``VectorLoading``, ``BlockVectorLoading``, ``MpsLoading``, ``EntangledManifoldEmbedding``, or ``FunctionLoading``. db: Active database session. Returns: A lightweight context wrapper summarizing the submission and next polling step. Raises: HTTPException: Raised with ``404`` if the experiment is unavailable for the user, or ``400`` if payload validation fails. operationId: load_classical_data_with_data_loading requestBody: content: application/json: schema: $ref: '#/components/schemas/ContextDataLoadingSubmitModel' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ContextDataLoadingJobModel' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyQuery: [] - APIKeyHeader: [] components: schemas: ContextDataLoadingSubmitModel: properties: experiment_id: anyOf: - type: string - type: 'null' title: Experiment Id default: '' name: anyOf: - type: string - type: 'null' title: Name default: '' description: anyOf: - type: string - type: 'null' title: Description default: '' parameters: additionalProperties: true type: object title: Parameters description: >- Mode-specific parameters. For `DistributionLoading`: `distribution_name`, `num_qubits`, `interval_start`, `interval_end`, `loc`, `scale`, `num_layers`, `truncation_cutoff` (+ optional scipy distribution shape args). For `VectorLoading`: `data`, `num_layers`, `truncation_cutoff`, `fine_tuning_iterations`. For `BlockVectorLoading`: `data`, (`num_blocks` or `target_num_qubits`), `num_layers`, `truncation_cutoff`, `fine_tuning_iterations`. For `EntangledManifoldEmbedding`: `data`, `density`, `real`, `periodicity`, `num_layers`, `truncation_cutoff`, `fine_tuning_iterations`. For `MpsLoading`: `mps`, `shape`, `num_layers`, `truncation_cutoff`, `fine_tuning_iterations`. For `FunctionLoading`: `func` (math expression string in the single variable `x`, e.g. `exp(-x**2)`), `interval_start`, `interval_end`, `num_layers`, `truncation_cutoff`, `fine_tuning_iterations`. num_qubits: anyOf: - type: integer - type: 'null' title: Num Qubits description: >- Optional qubit count. Required for `DistributionLoading` and `FunctionLoading`; optional for `VectorLoading` and `EntangledManifoldEmbedding`; ignored for `BlockVectorLoading`. distribution_name: anyOf: - type: string - type: 'null' title: Distribution Name description: Required for `DistributionLoading` (e.g. `norm`, `uniform`, `beta`). dl_type: type: string enum: - DistributionLoading - VectorLoading - BlockVectorLoading - EntangledManifoldEmbedding - MpsLoading - FunctionLoading title: Dl Type description: >- Data loading mode. Use one of: `DistributionLoading`, `VectorLoading`, `BlockVectorLoading`, `EntangledManifoldEmbedding`, `MpsLoading`, `FunctionLoading`. type: object required: - parameters - dl_type title: ContextDataLoadingSubmitModel description: >- Define payload for MCP classical-to-quantum data loading jobs. MCP-layer validation is limited to mode-specific required-key checks plus the ``BlockVectorLoading`` exclusivity rule implemented by :func:`haiqu.api.mcp.data_loading.validation.validate_data_loading_payload`. Attributes: experiment_id: Parent experiment identifier for the data-loading job. name: Optional job name. dl_type: Data-loading mode selector. parameters: Mode-specific parameters forwarded to the backend. num_qubits: Optional qubit count. Required for ``DistributionLoading``. distribution_name: Distribution identifier required for ``DistributionLoading``. examples: - distribution_name: norm dl_type: DistributionLoading experiment_id: exp-123 name: Normal distribution num_qubits: 4 parameters: interval_end: 3 interval_start: -3 loc: 0 num_layers: 1 scale: 1 truncation_cutoff: 0.000001 - distribution_name: meixner_cf dl_type: DistributionLoading experiment_id: exp-123 name: Meixner distribution num_qubits: 12 parameters: alpha: 1.5 beta: 0.5 delta: 0.5 interval_end: 3 interval_start: -3 loc: 0 mu: 0 num_layers: 1 scale: 1 truncation_cutoff: 0.000001 - dl_type: VectorLoading experiment_id: exp-123 name: Bell vector loading parameters: data: - 1 - 0 - 0 - 1 fine_tuning_iterations: 20 num_layers: 2 truncation_cutoff: 0.000001 - dl_type: BlockVectorLoading experiment_id: exp-123 name: Block vector loading parameters: data: - 0.5 - 0.2 - 1 - 14 - 0.3 - 5 - 0.2 - 0.6 fine_tuning_iterations: 20 num_blocks: 2 num_layers: 2 truncation_cutoff: 0.000001 - dl_type: EntangledManifoldEmbedding experiment_id: exp-123 name: Entangled manifold embedding parameters: data: - 1 - 2 - 3 - 4 - 5 density: 2 fine_tuning_iterations: 20 num_layers: 2 periodicity: false real: true truncation_cutoff: 0.000001 - dl_type: MpsLoading experiment_id: exp-123 name: Bell MPS loading parameters: fine_tuning_iterations: 20 mps: - - - - 1 - 0 - - - 0 - 1 - - - - 0.7071067811865475 - - 0 - - - 0 - - 0.7071067811865475 num_layers: 2 shape: plr truncation_cutoff: 0.000001 - dl_type: FunctionLoading experiment_id: exp-123 name: Gaussian function loading num_qubits: 6 parameters: fine_tuning_iterations: 20 func: exp(-x**2) interval_end: 3 interval_start: -3 num_layers: 2 truncation_cutoff: 0.000001 ContextDataLoadingJobModel: properties: context: type: string title: Context type: object required: - context title: ContextDataLoadingJobModel description: |- Represent context payload returned after data-loading submission. Attributes: context: Submission summary text including the created job ID and next polling step. This response model does not expose structured ``job_id`` or output ``circuit_id`` fields outside the text. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: APIKeyQuery: type: apiKey in: query name: HAIQU_API_KEY APIKeyHeader: type: apiKey in: header name: authorization ````